SCALING PROPERTIES OF NEURAL NETWORKS FOR JOB-SHOP SCHEDULING

This paper investigates the scaling properties of neural networks for solving job-shop scheduling problems. Specifically, the Tank-Hopfield linear programming network is modified to solve mixed integer linear p rogramming with the addition of step-function amplifiers. Using a line ar energy function, our approach avoids the traditional problems assoc iated with most Hopfield networks using quadratic energy functions. Al though our approach requires more hardware (in terms of processing ele ments and resistive interconnects) than a recent approach by Zhou et a l. [2], the neurons in the modified Tank-Hopfieid network do not perfo rm extensive calculations unlike those described by Zhou et al.